Back to skill

Security audit

TikTok B2B 引流台词生成器

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple TikTok B2B script generator with disclosed inputs and no executable or privileged behavior.

Before installing, confirm that the default contact URL and English-style opening fit your use case. The reviewed files do not show code execution, credential access, persistence, or destructive behavior.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The output example is entirely in English while the rest of the skill documentation is in Chinese, and the document does not state that users can choose the output language. This creates a natural-language locale policy concern because the skill appears to impose a specific language on generated content without explicit opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The prompt template requires the script to start in a specific English-style format using "Hi guys, this is Anna" as the example, while the rest of the skill is presented in Chinese and offers no language or locale choice. This can violate language/locale policy because it implicitly forces a particular language/presentation style on output without user opt-in or documented justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.